Principal Data Scientist - Causal Inference

An optimization platform for Consumer Packaged Goods (CPG) leaders, translating commercial, supply chain, and pricing complexity into dynamic decision workflows is seeking a Principal Data Scientist. This role centers on predictive modeling, causal inference, time-series forecasting, and optimization.

You'll build the analytical engines powering our CPG decision workflows — turning messy, multi-source retail data (POS, syndicated data, trade promotion inputs, inventory logs) into predictive insight, bridging historical reporting and forward-looking experimentation. They are advised by leading academic experts in causal inference and want someone excited to bridge academia and industry.

Location: Fully remote

Salary: Up to 180k base + equity

Responsibilities

• Build and scale ML models and optimization routines (demand forecasting, price elasticity, trade promotion optimization).
• Build statistical frameworks measuring incremental lift of business actions, isolating real revenue drivers from noise.
• Partner with engineering to structure noisy retail/billing data into clean, analysis-ready datasets.
• Design rigorous A/B and multivariate tests for new decision workflows and features.
• Translate statistical outputs into clear recommendations for product managers and executives

Requirements:

• Master's (PhD a plus) in Statistics, Data Science, Applied Math, Economics, or CS
• 3+ years commercial data science experience; or 1 year of experience + PhD
• Strong Python (Pandas, NumPy, Scikit-learn) and SQL
• Deep knowledge of time-series forecasting, regression, and ML methods
• Experience with cloud data warehouses (Snowflake, BigQuery, or similar)
• Dashboard/visualization skills (Tableau, PowerBI, Streamlit)
• Entrepreneurial mindset; comfortable shipping MVPs and iterating quickly

Preferred (not a must):

• CPG, e-commerce, or retail supply chain experience
• Bonus: potential to grow into a Head of Product or CPO role